让AI像专家一样精准推理，用理论保证可靠解题。
Artificial Expert Intelligence through PAC-reasoning
- 引入PAC推理框架，实现可控制精度的复杂问题分解
- 通过系统3机制，达成误差有界的推理能力
- 适合需要高可靠性推理的科研与工程场景
人工专家智能（AEI）旨在突破通用人工智能（AGI）和专用AI的局限，将领域专业知识与类顶尖人类专家的批判性、精确推理能力结合。现有AI系统虽在预设任务上表现优异，但在新颖问题求解中缺乏适应性与精确性。为此，AEI提出“可能近似正确（PAC）推理”范式，为复杂问题的可靠分解提供坚实的理论保障，并具备控制推理精度的实用机制。受人类思维分为直觉型系统1与反思型系统2的启发，该新型推理被称为系统3，体现科学方法的严谨性。由此，AEI构建了误差有界的推理时学习基础。
原文摘要 · Abstract (English)
Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts. Existing AI systems often excel at predefined tasks but struggle with adaptability and precision in novel problem-solving. To overcome this, AEI introduces a framework for ``Probably Approximately Correct (PAC) Reasoning". This paradigm provides robust theoretical guarantees for reliably decomposing complex problems, with a practical mechanism for controlling reasoning precision. In reference to the division of human thought into System 1 for intuitive thinking and System 2 for reflective reasoning~\citep{tversky1974judgment}, we refer to this new type of reasoning as System 3 for precise reasoning, inspired by the rigor of the scientific method. AEI thus establishes a foundation for error-bounded, inference-time learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。